Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Register Log in

Question regarding register renaming in modern processors

Status
Not open for further replies.
rahdirs

rahdirs

Advanced Member level 1
Joined
May 22, 2013
Messages
424
Helped
93
Reputation
192
Reaction score
91
Trophy points
1,308
Location
Mordor
Activity points
4,492
I was reading a paper from MICRO which says the following :

Register renaming was first proposed by Tomasulo in his well-known scheme for out-of order execution for the floating point unit of the IBM 360/91 in the 60s. In that scheme, destination operands were renamed using the identifier of the reservation station that would produce them. This scheme is not used by current microprocessors, since it requires that the reservation station be occupied by an instruction until its execution completes. Current microprocessors release the issue queue entries (reservation stations in Tomasulo’s nomenclature) right after being issued, which is more effective in terms of efficiency
Click to expand...

I understand the part where he says that TOMASULO is inefficient as it uses reservation station's ID till the instruction commits. But, i don't understand the statement
Current microprocessors release the issue queue entries (reservation stations in Tomasulo’s nomenclature) right after being issued, which is more effective in terms of efficiency
Click to expand...
 

Status
Not open for further replies.

Similar threads

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top